CONTEXT AWARE OBJECT RECOGNITION FOR IoT CONTROL

Abstract

A method and device for IoT control of objects in an environmental space includes capturing an image of one or more objects in the environmental space using a camera. The captured image is normalized for up/down orientation of the camera and one or more objects in the image are identified. At least one contextual attribute for the one or more objects is determined based on the captured image. A user control application for a network-connected object is accessed based on the determined at least one contextual attribute for the one or more objects.

1 . A method, implemented in a wireless transmit/receive unit (WTRU), the method comprising:
 capturing an image comprising one or more objects using one or more cameras;   normalizing the captured image into a standard format;   identifying the one or more objects in the normalized image;   determining at least one contextual attribute for the identified one or more objects based on the normalized image; and   accessing, based on the determined at least one contextual attribute for the identified one or more objects, one or more user control applications for one or more network-connected objects, wherein the one or more network-connected objects are determined from among the identified one or more objects.   
     
     
         2 . The method of  claim 1 , wherein normalizing the captured image into a standard format comprises normalizing the captured image for up/down orientation of the one or more cameras. 
     
     
         3 . The method of  claim 2 , wherein normalizing the captured image for up/down orientation comprises performing up/down off-axis normalization of the captured image. 
     
     
         4 . The method according to  claim 1 , wherein the at least one determined contextual attribute is any one of compass orientation of the identified one or more objects, visual characteristics of a wall or a floor, proximity of the identified one or more objects to other objects, and internet addresses and signal strengths of access points. 
     
     
         5 . The method according to  claim 1 , further comprising comparing the identified one or more objects to a library of object images and contextual attributes. 
     
     
         6 . The method of  claim 5 , further comprising:
 categorizing the identified one or more objects, based on the comparison, as one of at least one network-connected object of the one or more network-connected objects associated with a user control application of the one or more user control applications and at least one network-connected object of the one or more network-connected objects not associated with a user control application of the one or more user control applications.   
     
     
         7 . The method of  claim 6 , wherein on condition that the categorized identified one or more objects is at least one network-connected object associated with the user control application, further comprising:
 identifying the categorized identified one or more objects on a screen of a display as associated with the user control application; and   enabling touch activation on the screen for the user control application of the categorized identified one or more objects.   
     
     
         8 . The method of  claim 6 , wherein on condition that the categorized identified one or more objects is at least one network-connected object not associated with the user control application, further comprising:
 identifying the categorized identified one or more objects on a screen of a display as not associated with the user control application; and   enabling touch activation on the screen of an unregistered user control application for controlling the categorized identified one or more objects.   
     
     
         9 . The method of  claim 5 , further comprising categorizing the identified one or more objects based on the comparison as at least one network-connected object associated with a do not display directive. 
     
     
         10 . (canceled) 
     
     
         11 . The method according to  claim 1 , further comprising displaying on a user interface the accessed one or more user control applications. 
     
     
         12 . (canceled) 
     
     
         13 . A wireless transmit/receive unit (WTRU) comprising a processor, a transmitter, a receiver and memory, configured to:
 capture an image comprising one or more objects using one or more cameras;   normalize the captured image into a standard format;   identify the one or more objects in the normalized image;   determine at least one contextual attribute for the identified one or more objects based on the normalized image; and   access, based on the determined at least one contextual attribute for the identified one or more objects, one or more user control applications for one or more network-connected objects, wherein the one or more network-connected objects are determined from among the identified one or more objects.   
     
     
         14 . The WTRU of  claim 13 , wherein the WTRU is configured to normalize the captured image for up/down orientation of the one or more cameras. 
     
     
         15 . The WTRU of  claim 14 , wherein the WTRU is configured to perform up/down off-axis normalization of the captured image. 
     
     
         16 . The WTRU according to  claim 13 , wherein the at least one determined contextual attribute is any one of compass orientation of the identified one or more objects, visual characteristics of a wall or a floor, proximity of the identified one or more objects to other objects, and internet addresses and signal strengths of access points. 
     
     
         17 . The WTRU according to  claim 13 , further configured to compare the identified one or more objects to a library of object images and contextual attributes. 
     
     
         18 . The WTRU of  claim 17 , further configured to categorize the identified one or more objects, based on the comparison, as one of at least one network-connected object of the one or more network-connected objects associated with a user control application of the one or more user control applications and at least one network-connected object not associated with a user control application of the one or more user control applications. 
     
     
         19 . The WTRU of  claim 18 , wherein on condition that the categorized identified one or more objects is at least one network-connected object associated with the user control application, the WTRU is further configured to:
 identify the categorized identified one or more objects on a screen of a display as associated with the user control application; and   enable touch activation on the screen for the user control application of the categorized identified one or more objects.   
     
     
         20 . The WTRU of  claim 18 , wherein on condition that the categorized identified one or more objects is at least one network-connected object not associated with the user control application, the WTRU is further configured to:
 identify the categorized identified one or more objects on a screen of a display as not associated with the user control application; and   enable touch activation on the screen of an unregistered user control application for controlling the categorized identified one or more objects.   
     
     
         21 . The WTRU of  claim 17 , further configured to categorize the identified one or more objects based on the comparison as at least one network-connected object associated with a do not display directive. 
     
     
         22 . (canceled) 
     
     
         23 . The WTRU according to  claim 13 , wherein the WTRU is further configured to display on a user interface the accessed one or more user control applications. 
     
     
         24 . (canceled)